Skip to main content

BibTeX

@inProceedings{dannells-virk-2021-supervised-310123,
	title        = {A Supervised Machine Learning Approach for Post-OCR Error Detection for Historical Text },
	abstract     = {Training machine learning models with high accuracy requires careful feature engineering, which involves finding the best feature combinations and extracting their values from the data. The task becomes extremely laborious for specific problems such as post Optical Character Recognition (OCR) error detection because of the diversity of errors in the data. In this paper we present a machine learning approach which exploits character n-gram statistics as the only feature for the OCR error detection task. Our method achieves a significant improvement over the baseline reaching state-of-the-art results of 91% and 89% F1 measure on English and Swedish datasets respectively. We report various experiments to select the appropriate machine learning algorithm and to compare our approach to previously reported traditional approaches.},
	booktitle    = {Linköping Electronic Press Workshop and Conference Collection. Selected contributions from the Eighth Swedish Language Technology Conference (SLTC-2020), 25-27 November, 2020 },
	author       = {Dannélls, Dana and Virk, Shafqat},
	year         = {2021},
	publisher    = {Linköping Electronic Press },
	address      = {Linköping},
}